INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isine

-0.77

agascar

-0.76

 caut

-0.73

 therap

-0.72

ibrary

-0.71

izons

-0.71

uploads

-0.70

 Yard

-0.70

 Accessories

-0.70

phabet

-0.69

POSITIVE LOGITS

rough

0.71

stood

0.69

won

0.66

standing

0.65

hed

0.64

minded

0.63

ey

0.63

istic

0.62

onom

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.